{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TJH3BZ7SGTLK2HK7TR2NBR6HIV","short_pith_number":"pith:TJH3BZ7S","schema_version":"1.0","canonical_sha256":"9a4fb0e7f234d6ad1d5f9c74d0c7c745504350072640eb34d4f6812e18a7bdba","source":{"kind":"arxiv","id":"2606.11761","version":1},"attestation_state":"computed","paper":{"title":"RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Atif Hassan, Jiaul H. Paik, Swanand Khare","submitted_at":"2026-06-10T07:37:01Z","abstract_excerpt":"Dynamic data pruning techniques aim to reduce computational cost while minimizing information loss by periodically selecting representative subsets of input data during model training. However, existing methods often struggle to maintain strong worst-group accuracy, particularly at high pruning rates, across balanced and imbalanced datasets. To address this challenge, we propose RCAP, a Robust, Class-Aware, Probabilistic dynamic dataset pruning algorithm for classification tasks. RCAP applies a closed-form solution to estimate the fraction of samples to be included in the training subset for e"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.11761","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T07:37:01Z","cross_cats_sorted":[],"title_canon_sha256":"e17d5f83688250c32f41ec7b6e668dea382c8ca7cd84fda736dade36ebd2f0dd","abstract_canon_sha256":"1ab5afe0723b4ecfe6398fe4df8aeadd841140d951180a29cc5230547fab3184"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:06.561337Z","signature_b64":"wHY3Cv6TqM1+5bZYq+INNsaLi3c9CStwusFwByfvd2cb9lCLjxNfHZsIqBhcMiGorh0k1/Rot5VbsP5Dz3MXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a4fb0e7f234d6ad1d5f9c74d0c7c745504350072640eb34d4f6812e18a7bdba","last_reissued_at":"2026-06-11T01:10:06.560560Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:06.560560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Atif Hassan, Jiaul H. Paik, Swanand Khare","submitted_at":"2026-06-10T07:37:01Z","abstract_excerpt":"Dynamic data pruning techniques aim to reduce computational cost while minimizing information loss by periodically selecting representative subsets of input data during model training. However, existing methods often struggle to maintain strong worst-group accuracy, particularly at high pruning rates, across balanced and imbalanced datasets. To address this challenge, we propose RCAP, a Robust, Class-Aware, Probabilistic dynamic dataset pruning algorithm for classification tasks. RCAP applies a closed-form solution to estimate the fraction of samples to be included in the training subset for e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11761","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.11761/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.11761","created_at":"2026-06-11T01:10:06.560687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11761v1","created_at":"2026-06-11T01:10:06.560687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11761","created_at":"2026-06-11T01:10:06.560687+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJH3BZ7SGTLK","created_at":"2026-06-11T01:10:06.560687+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJH3BZ7SGTLK2HK7","created_at":"2026-06-11T01:10:06.560687+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJH3BZ7S","created_at":"2026-06-11T01:10:06.560687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJH3BZ7SGTLK2HK7TR2NBR6HIV","json":"https://pith.science/pith/TJH3BZ7SGTLK2HK7TR2NBR6HIV.json","graph_json":"https://pith.science/api/pith-number/TJH3BZ7SGTLK2HK7TR2NBR6HIV/graph.json","events_json":"https://pith.science/api/pith-number/TJH3BZ7SGTLK2HK7TR2NBR6HIV/events.json","paper":"https://pith.science/paper/TJH3BZ7S"},"agent_actions":{"view_html":"https://pith.science/pith/TJH3BZ7SGTLK2HK7TR2NBR6HIV","download_json":"https://pith.science/pith/TJH3BZ7SGTLK2HK7TR2NBR6HIV.json","view_paper":"https://pith.science/paper/TJH3BZ7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11761&json=true","fetch_graph":"https://pith.science/api/pith-number/TJH3BZ7SGTLK2HK7TR2NBR6HIV/graph.json","fetch_events":"https://pith.science/api/pith-number/TJH3BZ7SGTLK2HK7TR2NBR6HIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJH3BZ7SGTLK2HK7TR2NBR6HIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJH3BZ7SGTLK2HK7TR2NBR6HIV/action/storage_attestation","attest_author":"https://pith.science/pith/TJH3BZ7SGTLK2HK7TR2NBR6HIV/action/author_attestation","sign_citation":"https://pith.science/pith/TJH3BZ7SGTLK2HK7TR2NBR6HIV/action/citation_signature","submit_replication":"https://pith.science/pith/TJH3BZ7SGTLK2HK7TR2NBR6HIV/action/replication_record"}},"created_at":"2026-06-11T01:10:06.560687+00:00","updated_at":"2026-06-11T01:10:06.560687+00:00"}